Evolving an Artificial Visual Cortex for Object Recognition with Brain Programming
This chapter describes a new approach to synthesize an artificial visual cortex based on what we call brain programming. Primate brains have several distinctive features that help in the outstanding display of perception achieved by the visual system, including binocular vision, memory, learning, and recognition, to mention only a few. These features are obtained by a complex arrangement of highly interconnected and numerous cortical visual areas. This chapter describes a system composed of an artificial dorsal pathway, or where stream, and an artificial ventral pathway, or what stream, that are fused to create a kind of artificial visual cortex. The idea is to show that brain programming is able to evolve a high number of heterogeneous trees thanks to the hierarchical structure of our virtual brain. Thus, the proposal uses two key ideas: 1) the recognition of objects can be achieved by a hierarchical structure using the concept of function composition, 2) the evolved functions can be discovered through the application of multiple runs of genetic programming that works concurrently using the hierarchical structure. Experimental results provide evidence that high recognition rates could be achieved for a well-known multiclass object recognition problem.
KeywordsArtificial Visual Cortex Brain Programming Object Recognition
Unable to display preview. Download preview PDF.
- 3.Chang, C.C., Lin, C.J.: LIBSVM: A Library for Support Vector Machines. ACM Transactions on Intelligent Systems and Technology 2, 27:1–27:27 (2011), Software available at http://www.csie.ntu.edu.tw/~cjlin/libsvm
- 9.Holland, J.H.: Complex Adaptive Systems. Daedalus 121(1), 17–30 (1992)Google Scholar
- 11.Hubel, D.H.: Exploration of the primary visual cortex, 1955-78. Nature, 515–524 (October 1982)Google Scholar
- 12.Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148(3), 574–591 (1953)Google Scholar
- 14.Koch, C., Ullman, S.: Shifts in selective visual attention: towards the underlying neural circuitry. Hum. Neurobiol. 4(4), 219–227 (1985)Google Scholar
- 18.Milanese, R.: Detecting salient regions in an image: from biological evidence to computer implementation. PhD thesis, Department of Computer Science, University of Genova, Switzerland (December 1993)Google Scholar
- 21.Olague, G.: Evolutionary Computer Vision – The First Footprints (to appear)Google Scholar
- 27.Serre, T., Kouh, C., Cadieu, M., Knoblich, G., Kreiman, U., Poggio, T.: A Theory of Object Recognition: Computations and Circuits in the Feedforward Path of the Ventral Stream in Primate Visual Cortex. Technical report, Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory, CBCL-259 (2005)Google Scholar
- 30.Ullman, S., Vidal-Naquet, M., Sali, E.: Visual features of intermediate complexity and their use in classification. Nature Neuroscience 5(7), 682–687 (2002)Google Scholar